BIRCH clustering - Example with 'titanic' dataset
In this video, I tried implementing the BIRCH clustering algorithm using the Scikit-Learn library. I showed this example using the Titanic dataset available in the Seaborn library. I didn't explain any theory of BIRCH clustering in this video. If you are interested in knowing the theory of BIRCH clustering, then check out the Scikit-Learn documentation link.
GitHub address: https://github.com/randomaccess2023/M...
Scikit-Learn documentation link on BIRCH clustering: https://scikit-learn.org/stable/modul...
01:00 Import the required libraries
02:29 Load 'titanic' dataset
03:31 Select the features and targets
07:43 Fill NaN values
09:21 Replace categorical values with some indicator values
10:56 Perform preprocessing
11:31 Scaled dataframe
12:52 Perform 'BIRCH clustering' with 2 clusters
14:01 Add two new columns to the scaled dataframe
15:15 Clustering comparison between targets and predictions
19:54 Visualize predictions
#datascience #birchclustering #titanicdataset #jupyternotebook #scikitlearn #unsupervisedlearning #python